Commit Graph

  • 8fbf352ec6 docs: add more information about pretrained weights aarnphm-ec2-dev 2023-06-10 06:58:36 +00:00
  • c669d38dea fix(flan-t5): casting model to CUDA aarnphm-ec2-dev 2023-06-10 06:55:17 +00:00
  • afddaed08c fix(perf): respect per request information Aaron 2023-06-10 02:14:13 -04:00
  • e90d90e9a0 feat(docs): copy button from table list Aaron 2023-06-10 01:23:56 -04:00
  • 7d382ced4f chore(docs): update notes about flan-t5 Aaron 2023-06-10 00:13:58 -04:00
  • 9ffe1f40bf chore: rename LICENSE to LICENSE.md Chaoyu 2023-06-09 17:25:45 -07:00
  • e2b26adf2f chore(docs): update README.md Chaoyu 2023-06-09 17:13:14 -07:00
  • 1597d5d4bb chore(readme): update stablelm [generated] Aaron 2023-06-09 16:58:05 -04:00
  • bca133f389 revert: update metadata for Python 3.8 and 3.9 Aaron 2023-06-09 15:05:45 -04:00
  • 11cedce974 infra: bump to dev version of 0.0.33.dev0 [generated] Aaron Pham [bot] 2023-06-09 19:18:44 +00:00
  • 03ac525949 infra: prepare for release 0.0.32 [generated] v0.0.32 Aaron Pham [bot] 2023-06-09 19:05:09 +00:00
  • 9bbe1ff4bf chore(stablelm): make stablelm run explicitly with GPU Aaron 2023-06-09 14:57:12 -04:00
  • c51e944cb2 chore(version): remove support for 3.8 and 3.9 for now Aaron 2023-06-08 22:47:57 -04:00
  • b72317db67 fix(import): lazy load torch Aaron 2023-06-08 22:05:41 -04:00
  • 16df0f4393 chore(infra): increase timeout to 60m Aaron 2023-06-08 18:11:00 -04:00
  • d005760c68 infra: bump to dev version of 0.0.32.dev0 [generated] Aaron Pham [bot] 2023-06-08 22:15:29 +00:00
  • e2813f843e infra: prepare for release 0.0.31 [generated] v0.0.31 Aaron Pham [bot] 2023-06-08 22:04:19 +00:00
  • ebe5ae797e fix(script): avoid using private variable Aaron 2023-06-08 17:55:54 -04:00
  • f5edd4fcf4 feat(script): add easy script to release Aaron 2023-06-08 17:52:39 -04:00
  • f284c64370 docs: update release-notes run with ref for tags Aaron 2023-06-08 16:59:26 -04:00
  • acf78ce731 fix(saving): make sure to cleanup cuda cache after using default import aarnphm-ec2-dev 2023-06-08 21:10:27 +00:00
  • a451b03a0a infra: bump to dev version of 0.0.31.dev0 [generated] Aaron Pham [bot] 2023-06-08 21:10:01 +00:00
  • 55d584a986 infra: prepare for release 0.0.30 [generated] v0.0.30 Aaron Pham [bot] 2023-06-08 20:55:39 +00:00
  • 2f9bd2f6fe fix(packaging): make sure to add BENTOML_CONFIG_OPTIONS into Dockerfile aarnphm-ec2-dev 2023-06-08 20:32:52 +00:00
  • 71198b66cc revert: move release-notes to separate actions Aaron 2023-06-08 16:03:41 -04:00
  • 1902954463 infra: bump to dev version of 0.0.30.dev0 [generated] Aaron 2023-06-08 16:03:36 -04:00
  • 2db7663ba5 infra: prepare for release 0.0.29 [generated] v0.0.29 Aaron Pham [bot] 2023-06-08 19:56:51 +00:00
  • 42f8d0271c chore(model_name): shorten model name aarnphm-ec2-dev 2023-06-08 19:41:59 +00:00
  • d86fb322d0 fix(containerize): Install base openllm for non OpenLLM dev build aarnphm-ec2-dev 2023-06-08 19:29:39 +00:00
  • 1c9c9645a7 fix(label): make sure to convert labels to all string aarnphm-ec2-dev 2023-06-08 19:25:55 +00:00
  • 0f7840626d fix(cli): make sure to allow user to pass endpointu aarnphm-ec2-dev 2023-06-08 19:23:04 +00:00
  • f84b975a55 fix(llm): build to include openllm_client aarnphm-ec2-dev 2023-06-08 19:19:50 +00:00
  • e6dd1b1c39 docs: Update README.md Jian Shen 2023-06-09 03:02:53 +08:00
  • 15cb13839d fix(load_model): make sure to use correct implementation aarnphm-ec2-dev 2023-06-08 19:00:44 +00:00
  • a84661142c chore(cli): remove --local for query Aaron 2023-06-08 14:53:11 -04:00
  • 7a162402a1 fix(llm): make sure to use correct load_model Aaron 2023-06-08 14:50:58 -04:00
  • 20bc9153b1 fix(ci): checkout version on actions Aaron 2023-06-08 14:40:38 -04:00
  • 20416ab107 infra: bump to dev version of 0.0.29.dev0 [generated] Aaron 2023-06-08 14:40:29 -04:00
  • f6d6b08369 infra: prepare for release 0.0.28 [generated] v0.0.28 Aaron Pham [bot] 2023-06-08 13:25:55 +00:00
  • 400445da6f fix(deps): broken name for bitsandbytes Aaron 2023-06-08 09:19:05 -04:00
  • 067a7a8e81 chore(ci): add check script for README table update Aaron 2023-06-08 09:16:28 -04:00
  • c0418b76ec feat(infra): add tools for managing optional-dependencies Aaron 2023-06-08 08:57:19 -04:00
  • 23d98a2729 feat(tooling): add script to auto update readme table of supported models Aaron 2023-06-08 08:22:55 -04:00
  • 0680059a21 chore(ci): cleanup workflow Aaron 2023-06-08 05:28:56 -04:00
  • 5ecbc0017f infra: bump to dev version of 0.0.28.dev0 [generated] Aaron 2023-06-08 05:27:50 -04:00
  • 4c86f661ec infra: prepare for release 0.0.27 [generated] v0.0.27 Aaron Pham [bot] 2023-06-08 09:11:30 +00:00
  • e9e12a66a8 fix(falcon): custom load aarnphm-ec2-dev 2023-06-08 09:03:34 +00:00
  • 378b209d67 feat(llm): custom load_model Aaron 2023-06-08 04:07:07 -04:00
  • 4369395520 chore(docs): running formatter Aaron 2023-06-08 03:14:14 -04:00
  • 5060f22600 fix(stablelm): disable running on 8bit aarnphm-ec2-dev 2023-06-08 06:40:18 +00:00
  • e276b948f0 chore(stablelm): normalize keys name aarnphm-ec2-dev 2023-06-08 06:29:11 +00:00
  • 33d0af82a7 chore(readme): align badges to middle Aaron Pham 2023-06-07 18:33:27 -04:00
  • 66104a017f docs: Update Badge Jian Shen 2023-06-08 02:06:09 +08:00
  • f4c0ef6d0c docs: Add Badges Jian Shen 2023-06-08 01:58:20 +08:00
  • de273a7dd2 doc: Update Readme with Integrations Section Jian Shen 2023-06-08 01:36:05 +08:00
  • f2771bfe49 chore(cli): move back --version Aaron 2023-06-07 03:41:24 -04:00
  • afb5c7bead chore(deps): lowerbound tabulate to 0.9.0 aarnphm-ec2-dev 2023-06-07 06:57:59 +00:00
  • b794f75744 fix: move accelerate to fine-tune aarnphm-ec2-dev 2023-06-07 06:51:24 +00:00
  • 170be0ebc8 fix(cli): make sure make_tag to respect config trust_remote_code aarnphm-ec2-dev 2023-06-07 04:35:15 +00:00
  • ce7143060e chore(ci): to run release note on all tag Aaron 2023-06-07 00:24:25 -04:00
  • c960b3edff feat(client): add postprocess for processing client output call aarnphm-ec2-dev 2023-06-07 04:04:21 +00:00
  • 5ed71e7121 infra: bump to dev version of 0.0.27.dev0 [generated] Aaron 2023-06-07 00:24:11 -04:00
  • 3121576de6 infra: prepare for release 0.0.26 [generated] v0.0.26 Aaron Pham [bot] 2023-06-07 03:33:24 +00:00
  • d6d2de6748 feat(cli): prune Aaron 2023-06-06 23:24:50 -04:00
  • aa50b5279e fix(falcon): loading based on model registration Aaron 2023-06-06 22:42:28 -04:00
  • ffac6d8916 ui: improve usability with config Aaron 2023-06-06 19:29:21 -04:00
  • 45f022eea3 fix(dolly): no need to pass do_sample to pipeline Aaron 2023-06-06 18:46:01 -04:00
  • 8823c70e5a chore: rename variants to pretrained for consistency Aaron 2023-06-06 18:45:45 -04:00
  • 2a778a6fa6 fix(ci): update detached HEAD to main Aaron 2023-06-06 18:23:50 -04:00
  • 14d702a34f fix(dolly-v2): using pipeline for latest implementation aarnphm-ec2-dev 2023-06-06 22:21:40 +00:00
  • f9535d60e7 fix(deps): bound to 23.1 Aaron 2023-06-06 17:36:48 -04:00
  • aab8bdba18 infra: bump to dev version of 0.0.26.dev0 [generated] Aaron 2023-06-06 17:37:26 -04:00
  • f0db182753 infra: prepare for release 0.0.25 [generated] v0.0.25 Aaron Pham [bot] 2023-06-06 21:23:30 +00:00
  • f78d55f0fd fix(cli): type handling for specific container types Aaron 2023-06-06 17:18:25 -04:00
  • b7a6f5cd2a infra: bump to dev version of 0.0.25.dev0 [generated] Aaron 2023-06-06 17:18:08 -04:00
  • aa34f0f03b infra: prepare for release 0.0.24 [generated] v0.0.24 Aaron Pham [bot] 2023-06-06 19:59:06 +00:00
  • ed54a0b746 chore: fix type issue on 3.8 Aaron 2023-06-06 15:53:02 -04:00
  • b446b65642 chore(cli): remove alias and use build to be consistent with BentoML Aaron 2023-06-06 15:50:01 -04:00
  • fcc67824cb docs: Update README.md Jian Shen 2023-06-06 23:40:38 +08:00
  • f7ba6208c3 infra: bump to dev version of 0.0.24dev0 Aaron 2023-06-06 09:15:57 -04:00
  • f5ab01f2dd infra(release): update logic on push Aaron 2023-06-06 09:14:34 -04:00
  • 80ce543311 infra: prepare for release 0.0.23 [generated] v0.0.23 Aaron Pham [bot] 2023-06-06 12:52:21 +00:00
  • 44ac29b9dd infra: update release scripts to run on actions only Aaron 2023-06-06 08:44:14 -04:00
  • a0749d0a80 chore: update version message Aaron 2023-06-06 08:31:29 -04:00
  • 06f501247c infra: bump to dev version of 0.0.23.dev0 [generated] Aaron Pham [bot] 2023-06-06 12:22:41 +00:00
  • a1461fa39b infra: prepare for release 0.0.22 [generated] v0.0.22 Aaron Pham [bot] 2023-06-06 12:22:33 +00:00
  • dd7f1001d1 infra: set base BentoML to 1.0.21 Aaron 2023-06-06 08:15:17 -04:00
  • f373e0ad4f docs: chore and add section on integrating model Jian Shen 2023-06-06 13:38:20 +08:00
  • 1707beb7aa feat(cli): openllm query Aaron 2023-06-05 22:39:04 -04:00
  • 41a6bd03a6 docs: Readme and Developer Guide Jian Shen 2023-06-06 00:52:48 +08:00
  • f840222d12 feat(service): add timeout to metadata Aaron 2023-06-05 00:46:02 -07:00
  • 8ef4c9cb19 fix(types): broken import and add hints for client Aaron 2023-06-05 00:10:44 -07:00
  • b7420bf6ce chore: add assert license headers Aaron 2023-06-04 16:35:33 -07:00
  • ec941c95d5 chore: add license header Aaron 2023-06-04 16:22:20 -07:00
  • c5170c9c47 infra: bump to dev version of 0.0.22.dev0 [generated] Aaron Pham [bot] 2023-06-04 22:46:00 +00:00
  • c76ff987c3 infra: prepare for release 0.0.21 [generated] v0.0.21 Aaron Pham [bot] 2023-06-04 22:45:50 +00:00
  • 5ebe7e151a fix: set AUTHOR_NAME and AUTHOR_EMAIL for automatic release Aaron 2023-06-04 15:39:32 -07:00
  • 52e5f91bd1 infra: bump to dev version of 0.0.21.dev0 [generated] Aaron 2023-06-04 15:39:25 -07:00
  • 414341d8d0 infra: prepare for release 0.0.20 [generated] Aaron Pham [bot] 2023-06-04 22:31:13 +00:00
  • 352c2ee003 fix(ci): add prefix v for archive creation Aaron 2023-06-04 15:23:14 -07:00